Abhishek Aich

Abhishek Aich, Calvin-Khang Ta, Akash Gupta et al.

The majority of methods for crafting adversarial attacks have focused on scenes with a single dominant object (e.g., images from ImageNet). On the other hand, natural scenes include multiple dominant objects that are semantically related. Thus, it is crucial to explore designing attack strategies that look beyond learning on single-object scenes or attack single-object victim classifiers. Due to their inherent property of strong transferability of perturbations to unknown models, this paper presents the first approach of using generative models for adversarial attacks on multi-object scenes. In order to represent the relationships between different objects in the input scene, we leverage upon the open-sourced pre-trained vision-language model CLIP (Contrastive Language-Image Pre-training), with the motivation to exploit the encoded semantics in the language space along with the visual space. We call this attack approach Generative Adversarial Multi-object scene Attacks (GAMA). GAMA demonstrates the utility of the CLIP model as an attacker's tool to train formidable perturbation generators for multi-object scenes. Using the joint image-text features to train the generator, we show that GAMA can craft potent transferable perturbations in order to fool victim classifiers in various attack settings. For example, GAMA triggers ~16% more misclassification than state-of-the-art generative approaches in black-box settings where both the classifier architecture and data distribution of the attacker are different from the victim. Our code is available here: https://abhishekaich27.github.io/gama.html

Calvin-Khang Ta, Abhishek Aich, Akash Gupta et al.

Image enhancement approaches often assume that the noise is signal independent, and approximate the degradation model as zero-mean additive Gaussian. However, this assumption does not hold for biomedical imaging systems where sensor-based sources of noise are proportional to signal strengths, and the noise is better represented as a Poisson process. In this work, we explore a sparsity and dictionary learning-based approach and present a novel self-supervised learning method for single-image denoising where the noise is approximated as a Poisson process, requiring no clean ground-truth data. Specifically, we approximate traditional iterative optimization algorithms for image denoising with a recurrent neural network that enforces sparsity with respect to the weights of the network. Since the sparse representations are based on the underlying image, it is able to suppress the spurious components (noise) in the image patches, thereby introducing implicit regularization for denoising tasks through the network structure. Experiments on two bio-imaging datasets demonstrate that our method outperforms the state-of-the-art approaches in terms of PSNR and SSIM. Our qualitative results demonstrate that, in addition to higher performance on standard quantitative metrics, we are able to recover much more subtle details than other compared approaches. Our code is made publicly available at https://github.com/tacalvin/Poisson2Sparse

Abhishek Aich, Kuan-Chuan Peng, Amit K. Roy-Chowdhury

Most cross-domain unsupervised Video Anomaly Detection (VAD) works assume that at least few task-relevant target domain training data are available for adaptation from the source to the target domain. However, this requires laborious model-tuning by the end-user who may prefer to have a system that works ``out-of-the-box." To address such practical scenarios, we identify a novel target domain (inference-time) VAD task where no target domain training data are available. To this end, we propose a new `Zero-shot Cross-domain Video Anomaly Detection (zxvad)' framework that includes a future-frame prediction generative model setup. Different from prior future-frame prediction models, our model uses a novel Normalcy Classifier module to learn the features of normal event videos by learning how such features are different ``relatively" to features in pseudo-abnormal examples. A novel Untrained Convolutional Neural Network based Anomaly Synthesis module crafts these pseudo-abnormal examples by adding foreign objects in normal video frames with no extra training cost. With our novel relative normalcy feature learning strategy, zxvad generalizes and learns to distinguish between normal and abnormal frames in a new target domain without adaptation during inference. Through evaluations on common datasets, we show that zxvad outperforms the state-of-the-art (SOTA), regardless of whether task-relevant (i.e., VAD) source training data are available or not. Lastly, zxvad also beats the SOTA methods in inference-time efficiency metrics including the model size, total parameters, GPU energy consumption, and GMACs.

Abhishek Aich, Sparsh Garg, Vijay Kumar BG et al.

Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs), yet verification remains sparse: many slices are missing, making empirical failure rates unreliable. We propose SliceScorer, a deterministic scoring rule for missing-slice recommendation that combines (i) an exposure-based coverage prior to prioritize rare, under-tested regions, and (ii) a neighbor-failure prior that propagates risk from similar tested conditions. SliceScorer is deliberately simple - interpretable, auditable, and conservative - properties essential for safety-critical validation. For stress testing beyond the declared ODD, we embed SliceScorer within SliceNav, an LLM-orchestrated verification pipeline where the model interprets developer queries to select relevant operators (triage, scoring, acquisition, evaluation) and vocabulary extensions, composing verification workflows while keeping all scoring deterministic and auditable. Experiments on three driving VLMs (WiseAD, DriveMM, Cosmos-Reason2-2B) show that SliceNav surfaces high-risk coverage gaps more effectively than prior slice-discovery methods while maintaining diverse recommendations across the condition space. Ablations confirm both scoring components contribute, and qualitative analysis demonstrates end-to-end workflows from developer query to targeted evaluation.

Abhishek Aich, Shasha Li, Chengyu Song et al.

State-of-the-art generative model-based attacks against image classifiers overwhelmingly focus on single-object (i.e., single dominant object) images. Different from such settings, we tackle a more practical problem of generating adversarial perturbations using multi-object (i.e., multiple dominant objects) images as they are representative of most real-world scenes. Our goal is to design an attack strategy that can learn from such natural scenes by leveraging the local patch differences that occur inherently in such images (e.g. difference between the local patch on the object `person' and the object `bike' in a traffic scene). Our key idea is to misclassify an adversarial multi-object image by confusing the victim classifier for each local patch in the image. Based on this, we propose a novel generative attack (called Local Patch Difference or LPD-Attack) where a novel contrastive loss function uses the aforesaid local differences in feature space of multi-object scenes to optimize the perturbation generator. Through various experiments across diverse victim convolutional neural networks, we show that our approach outperforms baseline generative attacks with highly transferable perturbations when evaluated under different white-box and black-box settings.

Abhishek Aich, Samuel Schulter, Amit K. Roy-Chowdhury et al.

We aim to train a multi-task model such that users can adjust the desired compute budget and relative importance of task performances after deployment, without retraining. This enables optimizing performance for dynamically varying user needs, without heavy computational overhead to train and save models for various scenarios. To this end, we propose a multi-task model consisting of a shared encoder and task-specific decoders where both encoder and decoder channel widths are slimmable. Our key idea is to control the task importance by varying the capacities of task-specific decoders, while controlling the total computational cost by jointly adjusting the encoder capacity. This improves overall accuracy by allowing a stronger encoder for a given budget, increases control over computational cost, and delivers high-quality slimmed sub-architectures based on user's constraints. Our training strategy involves a novel 'Configuration-Invariant Knowledge Distillation' loss that enforces backbone representations to be invariant under different runtime width configurations to enhance accuracy. Further, we present a simple but effective search algorithm that translates user constraints to runtime width configurations of both the shared encoder and task decoders, for sampling the sub-architectures. The key rule for the search algorithm is to provide a larger computational budget to the higher preferred task decoder, while searching a shared encoder configuration that enhances the overall MTL performance. Various experiments on three multi-task benchmarks (PASCALContext, NYUDv2, and CIFAR100-MTL) with diverse backbone architectures demonstrate the advantage of our approach. For example, our method shows a higher controllability by ~33.5% in the NYUD-v2 dataset over prior methods, while incurring much less compute cost.

Qilong Zhangli, Di Liu, Abhishek Aich et al.

Leveraging multiple training datasets to scale up image segmentation models is beneficial for increasing robustness and semantic understanding. Individual datasets have well-defined ground truth with non-overlapping mask layouts and mutually exclusive semantics. However, merging them for multi-dataset training disrupts this harmony and leads to semantic inconsistencies; for example, the class "person" in one dataset and class "face" in another will require multilabel handling for certain pixels. Existing methods struggle with this setting, particularly when evaluated on label spaces mixed from the individual training sets. To overcome these issues, we introduce a simple yet effective multi-dataset training approach by integrating language-based embeddings of class names and label space-specific query embeddings. Our method maintains high performance regardless of the underlying inconsistencies between training datasets. Notably, on four benchmark datasets with label space inconsistencies during inference, we outperform previous methods by 1.6% mIoU for semantic segmentation, 9.1% PQ for panoptic segmentation, 12.1% AP for instance segmentation, and 3.0% in the newly proposed PIQ metric.

Sparsh Garg, Abhishek Aich

Obtaining high-quality fine-grained annotations for traffic signs is critical for accurate and safe decision-making in autonomous driving. Widely used datasets, such as Mapillary, often provide only coarse-grained labels - without distinguishing semantically important types such as stop signs or speed limit signs. To this end, we present a new validation set for traffic signs derived from the Mapillary dataset called Mapillary Vistas Validation for Traffic Signs (MVV), where we decompose composite traffic signs into granular, semantically meaningful categories. The dataset includes pixel-level instance masks and has been manually annotated by expert annotators to ensure label fidelity. Further, we benchmark several state-of-the-art VLMs against the self-supervised DINOv2 model on this dataset and show that DINOv2 consistently outperforms all VLM baselines-not only on traffic sign recognition, but also on heavily represented categories like vehicles and humans. Our analysis reveals significant limitations in current vision-language models for fine-grained visual understanding and establishes DINOv2 as a strong baseline for dense semantic matching in autonomous driving scenarios. This dataset and evaluation framework pave the way for more reliable, interpretable, and scalable perception systems. Code and data are available at: https://github.com/nec-labs-ma/relabeling

Abhishek Aich, Yumin Suh, Samuel Schulter et al.

A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions. With efficiency being a high priority for scaling such models, we observed that the state-of-the-art method Mask2Former uses 50% of its compute only on the transformer encoder. This is due to the retention of a full-length token-level representation of all backbone feature scales at each encoder layer. With this observation, we propose a strategy termed PROgressive Token Length SCALing for Efficient transformer encoders (PRO-SCALE) that can be plugged-in to the Mask2Former segmentation architecture to significantly reduce the computational cost. The underlying principle of PRO-SCALE is: progressively scale the length of the tokens with the layers of the encoder. This allows PRO-SCALE to reduce computations by a large margin with minimal sacrifice in performance (~52% encoder and ~27% overall GFLOPs reduction with no drop in performance on COCO dataset). Experiments conducted on public benchmarks demonstrates PRO-SCALE's flexibility in architectural configurations, and exhibits potential for extension beyond the settings of segmentation tasks to encompass object detection. Code here: https://github.com/abhishekaich27/proscale-pytorch

Shasha Li, Abhishek Aich, Shitong Zhu et al.

When compared to the image classification models, black-box adversarial attacks against video classification models have been largely understudied. This could be possible because, with video, the temporal dimension poses significant additional challenges in gradient estimation. Query-efficient black-box attacks rely on effectively estimated gradients towards maximizing the probability of misclassifying the target video. In this work, we demonstrate that such effective gradients can be searched for by parameterizing the temporal structure of the search space with geometric transformations. Specifically, we design a novel iterative algorithm Geometric TRAnsformed Perturbations (GEO-TRAP), for attacking video classification models. GEO-TRAP employs standard geometric transformation operations to reduce the search space for effective gradients into searching for a small group of parameters that define these operations. This group of parameters describes the geometric progression of gradients, resulting in a reduced and structured search space. Our algorithm inherently leads to successful perturbations with surprisingly few queries. For example, adversarial examples generated from GEO-TRAP have better attack success rates with ~73.55% fewer queries compared to the state-of-the-art method for video adversarial attacks on the widely used Jester dataset. Overall, our algorithm exposes vulnerabilities of diverse video classification models and achieves new state-of-the-art results under black-box settings on two large datasets. Code is available here: https://github.com/sli057/Geo-TRAP

Mauricio Soroco, Francesco Pittaluga, Zaid Tasneem et al.

Ensuring safety in autonomous driving requires scalable generation of realistic, controllable driving scenes beyond what real-world testing provides. Yet existing instruction guided image editors, trained on object-centric or artistic data, struggle with dense, safety-critical driving layouts. We propose HorizonWeaver, which tackles three fundamental challenges in driving scene editing: (1) multi-level granularity, requiring coherent object- and scene-level edits in dense environments; (2) rich high-level semantics, preserving diverse objects while following detailed instructions; and (3) ubiquitous domain shifts, handling changes in climate, layout, and traffic across unseen environments. The core of HorizonWeaver is a set of complementary contributions across data, model, and training: (1) Data: Large-scale dataset generation, where we build a paired real/synthetic dataset from Boreas, nuScenes, and Argoverse2 to improve generalization; (2) Model: Language-Guided Masks for fine-grained editing, where semantics-enriched masks and prompts enable precise, language-guided edits; and (3) Training: Content preservation and instruction alignment, where joint losses enforce scene consistency and instruction fidelity. Together, HorizonWeaver provides a scalable framework for photorealistic, instruction-driven editing of complex driving scenes, collecting 255K images across 13 editing categories and outperforming prior methods in L1, CLIP, and DINO metrics, achieving +46.4% user preference and improving BEV segmentation IoU by +33%. Project page: https://msoroco.github.io/horizonweaver/

Manyi Yao, Bingbing Zhuang, Sparsh Garg et al.

Grounding large language models (LLMs) in domain-specific tasks like post-hoc dash-cam driving video analysis is challenging due to their general-purpose training and lack of structured inductive biases. As vision is often the sole modality available for such analysis (i.e., no LiDAR, GPS, etc.), existing video-based vision-language models (V-VLMs) struggle with spatial reasoning, causal inference, and explainability of events in the input video. To this end, we introduce iFinder, a structured semantic grounding framework that decouples perception from reasoning by translating dash-cam videos into a hierarchical, interpretable data structure for LLMs. iFinder operates as a modular, training-free pipeline that employs pretrained vision models to extract critical cues -- object pose, lane positions, and object trajectories -- which are hierarchically organized into frame- and video-level structures. Combined with a three-block prompting strategy, it enables step-wise, grounded reasoning for the LLM to refine a peer V-VLM's outputs and provide accurate reasoning. Evaluations on four public dash-cam video benchmarks show that iFinder's proposed grounding with domain-specific cues, especially object orientation and global context, significantly outperforms end-to-end V-VLMs on four zero-shot driving benchmarks, with up to 39% gains in accident reasoning accuracy. By grounding LLMs with driving domain-specific representations, iFinder offers a zero-shot, interpretable, and reliable alternative to end-to-end V-VLMs for post-hoc driving video understanding.

Manyi Yao, Abhishek Aich, Yumin Suh et al.

Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be taxing on deployed devices. One way to overcome this challenge is by adapting the computation level to the specific needs of the input image rather than the current one-size-fits-all approach. To this end, we introduce ECO-M2F or EffiCient TransfOrmer Encoders for Mask2Former-style models. Noting that the encoder module of M2F-style models incur high resource-intensive computations, ECO-M2F provides a strategy to self-select the number of hidden layers in the encoder, conditioned on the input image. To enable this self-selection ability for providing a balance between performance and computational efficiency, we present a three step recipe. The first step is to train the parent architecture to enable early exiting from the encoder. The second step is to create an derived dataset of the ideal number of encoder layers required for each training example. The third step is to use the aforementioned derived dataset to train a gating network that predicts the number of encoder layers to be used, conditioned on the input image. Additionally, to change the computational-accuracy tradeoff, only steps two and three need to be repeated which significantly reduces retraining time. Experiments on the public datasets show that the proposed approach reduces expected encoder computational cost while maintaining performance, adapts to various user compute resources, is flexible in architecture configurations, and can be extended beyond the segmentation task to object detection.

Akash Gupta, Abhishek Aich, Kevin Rodriguez et al.

While machine learning approaches have shown remarkable performance in biomedical image analysis, most of these methods rely on high-quality and accurate imaging data. However, collecting such data requires intensive and careful manual effort. One of the major challenges in imaging the Shoot Apical Meristem (SAM) of Arabidopsis thaliana, is that the deeper slices in the z-stack suffer from different perpetual quality-related problems like poor contrast and blurring. These quality-related issues often lead to the disposal of the painstakingly collected data with little to no control on quality while collecting the data. Therefore, it becomes necessary to employ and design techniques that can enhance the images to make them more suitable for further analysis. In this paper, we propose a data-driven Deep Quantized Latent Representation (DQLR) methodology for high-quality image reconstruction in the Shoot Apical Meristem (SAM) of Arabidopsis thaliana. Our proposed framework utilizes multiple consecutive slices in the z-stack to learn a low dimensional latent space, quantize it and subsequently perform reconstruction using the quantized representation to obtain sharper images. Experiments on a publicly available dataset validate our methodology showing promising results.

Abhishek Aich, Meng Zheng, Srikrishna Karanam et al.

Despite much recent progress in video-based person re-identification (re-ID), the current state-of-the-art still suffers from common real-world challenges such as appearance similarity among various people, occlusions, and frame misalignment. To alleviate these problems, we propose Spatio-Temporal Representation Factorization (STRF), a flexible new computational unit that can be used in conjunction with most existing 3D convolutional neural network architectures for re-ID. The key innovations of STRF over prior work include explicit pathways for learning discriminative temporal and spatial features, with each component further factorized to capture complementary person-specific appearance and motion information. Specifically, temporal factorization comprises two branches, one each for static features (e.g., the color of clothes) that do not change much over time, and dynamic features (e.g., walking patterns) that change over time. Further, spatial factorization also comprises two branches to learn both global (coarse segments) as well as local (finer segments) appearance features, with the local features particularly useful in cases of occlusion or spatial misalignment. These two factorization operations taken together result in a modular architecture for our parameter-wise light STRF unit that can be plugged in between any two 3D convolutional layers, resulting in an end-to-end learning framework. We empirically show that STRF improves performance of various existing baseline architectures while demonstrating new state-of-the-art results using standard person re-ID evaluation protocols on three benchmarks.

Abhishek Aich

In this report, we present a theoretical support of the continual learning method \textbf{Elastic Weight Consolidation}, introduced in paper titled `Overcoming catastrophic forgetting in neural networks'. Being one of the most cited paper in regularized methods for continual learning, this report disentangles the underlying concept of the proposed objective function. We assume that the reader is aware of the basic terminologies of continual learning.

Akash Gupta, Abhishek Aich, Amit K. Roy-Chowdhury

Existing works address the problem of generating high frame-rate sharp videos by separately learning the frame deblurring and frame interpolation modules. Most of these approaches have a strong prior assumption that all the input frames are blurry whereas in a real-world setting, the quality of frames varies. Moreover, such approaches are trained to perform either of the two tasks - deblurring or interpolation - in isolation, while many practical situations call for both. Different from these works, we address a more realistic problem of high frame-rate sharp video synthesis with no prior assumption that input is always blurry. We introduce a novel architecture, Adaptive Latent Attention Network (ALANET), which synthesizes sharp high frame-rate videos with no prior knowledge of input frames being blurry or not, thereby performing the task of both deblurring and interpolation. We hypothesize that information from the latent representation of the consecutive frames can be utilized to generate optimized representations for both frame deblurring and frame interpolation. Specifically, we employ combination of self-attention and cross-attention module between consecutive frames in the latent space to generate optimized representation for each frame. The optimized representation learnt using these attention modules help the model to generate and interpolate sharp frames. Extensive experiments on standard datasets demonstrate that our method performs favorably against various state-of-the-art approaches, even though we tackle a much more difficult problem.

Abhishek Aich, Akash Gupta, Rameswar Panda et al.

Most of the existing works in video synthesis focus on generating videos using adversarial learning. Despite their success, these methods often require input reference frame or fail to generate diverse videos from the given data distribution, with little to no uniformity in the quality of videos that can be generated. Different from these methods, we focus on the problem of generating videos from latent noise vectors, without any reference input frames. To this end, we develop a novel approach that jointly optimizes the input latent space, the weights of a recurrent neural network and a generator through non-adversarial learning. Optimizing for the input latent space along with the network weights allows us to generate videos in a controlled environment, i.e., we can faithfully generate all videos the model has seen during the learning process as well as new unseen videos. Extensive experiments on three challenging and diverse datasets well demonstrate that our approach generates superior quality videos compared to the existing state-of-the-art methods.